Karthik Sridharan

Online Learning with Unknown Constraints ICML 2025 Optimization, Isoperimetric Inequalities, and Sampling via Lyapunov Potentials COLT 2025 System-Aware Unlearning Algorithms: Use Lesser, Forget Faster ICML 2025 Contextual Bandits and Imitation Learning with Preference-Based Active Queries NeurIPS 2023 Selective Sampling and Imitation Learning via Online Regression NeurIPS 2023 From Gradient Flow on Population Loss to Learning with Stochastic Gradient Descent NeurIPS 2022 Guarantees for Epsilon-Greedy Reinforcement Learning with Function Approximation ICML 2022 On the Complexity of Adversarial Decision Making NeurIPS 2022 Agnostic Reinforcement Learning with Low-Rank MDPs and Rich Observations NeurIPS 2021 SGD: The Role of Implicit Regularization, Batch-size and Multiple-epochs NeurIPS 2021 Online learning with dynamics: A minimax perspective NeurIPS 2020 Reinforcement Learning with Feedback Graphs NeurIPS 2020 Second-Order Information in Non-Convex Stochastic Optimization: Power and Limitations COLT 2020 Distributed Learning with Sublinear Communication ICML 2019 Hypothesis Set Stability and Generalization NeurIPS 2019 Optimization with Non-Differentiable Constraints with Applications to Fairness, Recall, Churn, and Other Goals JMLR 2019 The Complexity of Making the Gradient Small in Stochastic Convex Optimization COLT 2019 Training Well-Generalizing Classifiers for Fairness Metrics and Other Data-Dependent Constraints ICML 2019 Two-Player Games for Efficient Non-Convex Constrained Optimization ALT 2019 Algorithmic Learning Theory ALT 2018: Preface ALT 2018 Inference in Sparse Graphs with Pairwise Measurements and Side Information AISTATS 2018 Logistic Regression: The Importance of Being Improper COLT 2018 Online Learning: Sufficient Statistics and the Burkholder Method COLT 2018 Small-loss bounds for online learning with partial information COLT 2018 Uniform Convergence of Gradients for Non-Convex Learning and Optimization NeurIPS 2018 Efficient Online Multiclass Prediction on Graphs via Surrogate Losses AISTATS 2017 On Equivalence of Martingale Tail Bounds and Deterministic Regret Inequalities COLT 2017 Parameter-Free Online Learning via Model Selection NeurIPS 2017 ZigZag: A New Approach to Adaptive Online Learning COLT 2017 BISTRO: An Efficient Relaxation-Based Method for Contextual Bandits ICML 2016 Exploiting the Structure: Stochastic Gradient Methods Using Raw Clusters NeurIPS 2016 Learning in Games: Robustness of Fast Convergence NeurIPS 2016 Private Causal Inference AISTATS 2016 Adaptive Online Learning NeurIPS 2015 Hierarchies of Relaxations for Online Prediction Problems with Evolving Constraints COLT 2015 Learning with Square Loss: Localization through Offset Rademacher Complexity COLT 2015 Online Learning via Sequential Complexities JMLR 2015 Online Optimization : Competing with Dynamic Comparators AISTATS 2015 Online Non-Parametric Regression COLT 2014 Competing With Strategies COLT 2013 Localization and Adaptation in Online Learning AISTATS 2013 Online Learning with Predictable Sequences COLT 2013 Optimization, Learning, and Games with Predictable Sequences NeurIPS 2013 Relax and Randomize : From Value to Algorithms NeurIPS 2012 Selective Sampling and Active Learning from Single and Multiple Teachers JMLR 2012 Better Mini-Batch Algorithms via Accelerated Gradient Methods NeurIPS 2011 Complexity-Based Approach to Calibration with Checking Rules COLT 2011 Online Learning: Beyond Regret COLT 2011 Online Learning: Stochastic, Constrained, and Smoothed Adversaries NeurIPS 2011 On the Universality of Online Mirror Descent NeurIPS 2011 Learnability, Stability and Uniform Convergence JMLR 2010 Online Learning: Random Averages, Combinatorial Parameters, and Learnability NeurIPS 2010 Smoothness, Low Noise and Fast Rates NeurIPS 2010 Fast Rates for Regularized Objectives NeurIPS 2008 On the Complexity of Linear Prediction: Risk Bounds, Margin Bounds, and Regularization NeurIPS 2008